@AdinaYakup: Keye VL 2.0-30B-A3B New multimodal model from @KwaiKeye 30B/3B active - Apache 2.0 256K context via DeepSeek Sparse Att…
Summary
KwaiKeye releases Keye VL 2.0-30B-A3B, a multimodal model with 30B total / 3B active parameters, 256K context via DeepSeek Sparse Attention, and Apache 2.0 license, claiming it matches Qwen3 VL and Gemini 3 in accuracy.
View Cached Full Text
Cached at: 06/01/26, 01:23 PM
Keye VL 2.0-30B-A3B 🔥 New multimodal model from @KwaiKeye
✨ 30B/3B active - Apache 2.0 ✨ 256K context via DeepSeek Sparse Attention (probably the first model to ship this in production?👀) ✨ Gets MORE accurate as you feed it more frames ✨ Matchs Qwen3 VL and Gemini 3 https://t.co/B2MO3zMIad
Similar Articles
Kwai-Keye/Keye-VL-2.0-30B-A3B
Kwai-Keye releases Keye-VL-2.0-30B-A3B, a 30B-class vision-language model with advanced video understanding, sparse attention, and agent capabilities, achieving top benchmarks.
Keye-VL-2.0-30B-A3B -- Introducing DSA attention into multimodality for the first time
Kwai releases Keye-VL-2.0-30B-A3B, a 30B-class multimodal base model that introduces DSA attention to multimodality for the first time, targeting long-video understanding and agent capabilities.
Kwai Keye-VL-2.0 Technical Report
This technical report presents Kwai Keye-VL-2.0, an open-source Mixture-of-Experts multimodal foundation model designed for long-video understanding and agentic intelligence, leveraging DeepSeek Sparse Attention and cross-modal distillation to achieve state-of-the-art performance among similar-scale models.
@AdinaYakup: Step-3.7-Flash New VL model from @StepFun_ai 198B / 11B active - MoE 256K context 3 reasoning level Up to 400 tokens/sec
StepFun releases Step-3.7-Flash, a new large vision-language MoE model with 198B parameters (11B active), 256K context, and up to 400 tokens/sec inference speed.
Qwen3.8-27B
Qwen released open weights for Qwen3.8-27B, a native multimodal dense model with 27B parameters that outperforms Qwen3.7-Plus, supports 262K native context extendable to 1M, and is licensed under Apache 2.0.